| 1 |
.TH PCRE 3 "14 April 2012" "PCRE 8.31"
|
| 2 |
.SH NAME
|
| 3 |
PCRE - Perl-compatible regular expressions
|
| 4 |
.sp
|
| 5 |
.B #include <pcre.h>
|
| 6 |
.
|
| 7 |
.
|
| 8 |
.SH "PCRE 16-BIT API BASIC FUNCTIONS"
|
| 9 |
.rs
|
| 10 |
.sp
|
| 11 |
.SM
|
| 12 |
.B pcre16 *pcre16_compile(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP,
|
| 13 |
.ti +5n
|
| 14 |
.B const char **\fIerrptr\fP, int *\fIerroffset\fP,
|
| 15 |
.ti +5n
|
| 16 |
.B const unsigned char *\fItableptr\fP);
|
| 17 |
.PP
|
| 18 |
.B pcre16 *pcre16_compile2(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP,
|
| 19 |
.ti +5n
|
| 20 |
.B int *\fIerrorcodeptr\fP,
|
| 21 |
.ti +5n
|
| 22 |
.B const char **\fIerrptr\fP, int *\fIerroffset\fP,
|
| 23 |
.ti +5n
|
| 24 |
.B const unsigned char *\fItableptr\fP);
|
| 25 |
.PP
|
| 26 |
.B pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP,
|
| 27 |
.ti +5n
|
| 28 |
.B const char **\fIerrptr\fP);
|
| 29 |
.PP
|
| 30 |
.B void pcre16_free_study(pcre16_extra *\fIextra\fP);
|
| 31 |
.PP
|
| 32 |
.B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
|
| 33 |
.ti +5n
|
| 34 |
.B "PCRE_SPTR16 \fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
|
| 35 |
.ti +5n
|
| 36 |
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
|
| 37 |
.PP
|
| 38 |
.B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
|
| 39 |
.ti +5n
|
| 40 |
.B "PCRE_SPTR16 \fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
|
| 41 |
.ti +5n
|
| 42 |
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
|
| 43 |
.ti +5n
|
| 44 |
.B int *\fIworkspace\fP, int \fIwscount\fP);
|
| 45 |
.
|
| 46 |
.
|
| 47 |
.SH "PCRE 16-BIT API STRING EXTRACTION FUNCTIONS"
|
| 48 |
.rs
|
| 49 |
.sp
|
| 50 |
.B int pcre16_copy_named_substring(const pcre16 *\fIcode\fP,
|
| 51 |
.ti +5n
|
| 52 |
.B PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
|
| 53 |
.ti +5n
|
| 54 |
.B int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,
|
| 55 |
.ti +5n
|
| 56 |
.B PCRE_UCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);
|
| 57 |
.PP
|
| 58 |
.B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
|
| 59 |
.ti +5n
|
| 60 |
.B int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR16 *\fIbuffer\fP,
|
| 61 |
.ti +5n
|
| 62 |
.B int \fIbuffersize\fP);
|
| 63 |
.PP
|
| 64 |
.B int pcre16_get_named_substring(const pcre16 *\fIcode\fP,
|
| 65 |
.ti +5n
|
| 66 |
.B PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
|
| 67 |
.ti +5n
|
| 68 |
.B int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,
|
| 69 |
.ti +5n
|
| 70 |
.B PCRE_SPTR16 *\fIstringptr\fP);
|
| 71 |
.PP
|
| 72 |
.B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP,
|
| 73 |
.ti +5n
|
| 74 |
.B PCRE_SPTR16 \fIname\fP);
|
| 75 |
.PP
|
| 76 |
.B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP,
|
| 77 |
.ti +5n
|
| 78 |
.B PCRE_SPTR16 \fIname\fP, PCRE_UCHAR16 **\fIfirst\fP, PCRE_UCHAR16 **\fIlast\fP);
|
| 79 |
.PP
|
| 80 |
.B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
|
| 81 |
.ti +5n
|
| 82 |
.B int \fIstringcount\fP, int \fIstringnumber\fP,
|
| 83 |
.ti +5n
|
| 84 |
.B PCRE_SPTR16 *\fIstringptr\fP);
|
| 85 |
.PP
|
| 86 |
.B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP,
|
| 87 |
.ti +5n
|
| 88 |
.B int *\fIovector\fP, int \fIstringcount\fP, "PCRE_SPTR16 **\fIlistptr\fP);"
|
| 89 |
.PP
|
| 90 |
.B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP);
|
| 91 |
.PP
|
| 92 |
.B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP);
|
| 93 |
.
|
| 94 |
.
|
| 95 |
.SH "PCRE 16-BIT API AUXILIARY FUNCTIONS"
|
| 96 |
.rs
|
| 97 |
.sp
|
| 98 |
.B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
|
| 99 |
.PP
|
| 100 |
.B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP);
|
| 101 |
.PP
|
| 102 |
.B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP,
|
| 103 |
.ti +5n
|
| 104 |
.B pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);
|
| 105 |
.PP
|
| 106 |
.B const unsigned char *pcre16_maketables(void);
|
| 107 |
.PP
|
| 108 |
.B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
|
| 109 |
.ti +5n
|
| 110 |
.B int \fIwhat\fP, void *\fIwhere\fP);
|
| 111 |
.PP
|
| 112 |
.B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP);
|
| 113 |
.PP
|
| 114 |
.B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP);
|
| 115 |
.PP
|
| 116 |
.B const char *pcre16_version(void);
|
| 117 |
.PP
|
| 118 |
.B int pcre16_pattern_to_host_byte_order(pcre16 *\fIcode\fP,
|
| 119 |
.ti +5n
|
| 120 |
.B pcre16_extra *\fIextra\fP, const unsigned char *\fItables\fP);
|
| 121 |
.
|
| 122 |
.
|
| 123 |
.SH "PCRE 16-BIT API INDIRECTED FUNCTIONS"
|
| 124 |
.rs
|
| 125 |
.sp
|
| 126 |
.B void *(*pcre16_malloc)(size_t);
|
| 127 |
.PP
|
| 128 |
.B void (*pcre16_free)(void *);
|
| 129 |
.PP
|
| 130 |
.B void *(*pcre16_stack_malloc)(size_t);
|
| 131 |
.PP
|
| 132 |
.B void (*pcre16_stack_free)(void *);
|
| 133 |
.PP
|
| 134 |
.B int (*pcre16_callout)(pcre16_callout_block *);
|
| 135 |
.
|
| 136 |
.
|
| 137 |
.SH "PCRE 16-BIT API 16-BIT-ONLY FUNCTION"
|
| 138 |
.rs
|
| 139 |
.sp
|
| 140 |
.B int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *\fIoutput\fP,
|
| 141 |
.ti +5n
|
| 142 |
.B PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP,
|
| 143 |
.ti +5n
|
| 144 |
.B int \fIkeep_boms\fP);
|
| 145 |
.
|
| 146 |
.
|
| 147 |
.SH "THE PCRE 16-BIT LIBRARY"
|
| 148 |
.rs
|
| 149 |
.sp
|
| 150 |
Starting with release 8.30, it is possible to compile a PCRE library that
|
| 151 |
supports 16-bit character strings, including UTF-16 strings, as well as or
|
| 152 |
instead of the original 8-bit library. The majority of the work to make this
|
| 153 |
possible was done by Zoltan Herczeg. The two libraries contain identical sets
|
| 154 |
of functions, used in exactly the same way. Only the names of the functions and
|
| 155 |
the data types of their arguments and results are different. To avoid
|
| 156 |
over-complication and reduce the documentation maintenance load, most of the
|
| 157 |
PCRE documentation describes the 8-bit library, with only occasional references
|
| 158 |
to the 16-bit library. This page describes what is different when you use the
|
| 159 |
16-bit library.
|
| 160 |
.P
|
| 161 |
WARNING: A single application can be linked with both libraries, but you must
|
| 162 |
take care when processing any particular pattern to use functions from just one
|
| 163 |
library. For example, if you want to study a pattern that was compiled with
|
| 164 |
\fBpcre16_compile()\fP, you must do so with \fBpcre16_study()\fP, not
|
| 165 |
\fBpcre_study()\fP, and you must free the study data with
|
| 166 |
\fBpcre16_free_study()\fP.
|
| 167 |
.
|
| 168 |
.
|
| 169 |
.SH "THE HEADER FILE"
|
| 170 |
.rs
|
| 171 |
.sp
|
| 172 |
There is only one header file, \fBpcre.h\fP. It contains prototypes for all the
|
| 173 |
functions in both libraries, as well as definitions of flags, structures, error
|
| 174 |
codes, etc.
|
| 175 |
.
|
| 176 |
.
|
| 177 |
.SH "THE LIBRARY NAME"
|
| 178 |
.rs
|
| 179 |
.sp
|
| 180 |
In Unix-like systems, the 16-bit library is called \fBlibpcre16\fP, and can
|
| 181 |
normally be accesss by adding \fB-lpcre16\fP to the command for linking an
|
| 182 |
application that uses PCRE.
|
| 183 |
.
|
| 184 |
.
|
| 185 |
.SH "STRING TYPES"
|
| 186 |
.rs
|
| 187 |
.sp
|
| 188 |
In the 8-bit library, strings are passed to PCRE library functions as vectors
|
| 189 |
of bytes with the C type "char *". In the 16-bit library, strings are passed as
|
| 190 |
vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an
|
| 191 |
appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In
|
| 192 |
very many environments, "short int" is a 16-bit data type. When PCRE is built,
|
| 193 |
it defines PCRE_UCHAR16 as "short int", but checks that it really is a 16-bit
|
| 194 |
data type. If it is not, the build fails with an error message telling the
|
| 195 |
maintainer to modify the definition appropriately.
|
| 196 |
.
|
| 197 |
.
|
| 198 |
.SH "STRUCTURE TYPES"
|
| 199 |
.rs
|
| 200 |
.sp
|
| 201 |
The types of the opaque structures that are used for compiled 16-bit patterns
|
| 202 |
and JIT stacks are \fBpcre16\fP and \fBpcre16_jit_stack\fP respectively. The
|
| 203 |
type of the user-accessible structure that is returned by \fBpcre16_study()\fP
|
| 204 |
is \fBpcre16_extra\fP, and the type of the structure that is used for passing
|
| 205 |
data to a callout function is \fBpcre16_callout_block\fP. These structures
|
| 206 |
contain the same fields, with the same names, as their 8-bit counterparts. The
|
| 207 |
only difference is that pointers to character strings are 16-bit instead of
|
| 208 |
8-bit types.
|
| 209 |
.
|
| 210 |
.
|
| 211 |
.SH "16-BIT FUNCTIONS"
|
| 212 |
.rs
|
| 213 |
.sp
|
| 214 |
For every function in the 8-bit library there is a corresponding function in
|
| 215 |
the 16-bit library with a name that starts with \fBpcre16_\fP instead of
|
| 216 |
\fBpcre_\fP. The prototypes are listed above. In addition, there is one extra
|
| 217 |
function, \fBpcre16_utf16_to_host_byte_order()\fP. This is a utility function
|
| 218 |
that converts a UTF-16 character string to host byte order if necessary. The
|
| 219 |
other 16-bit functions expect the strings they are passed to be in host byte
|
| 220 |
order.
|
| 221 |
.P
|
| 222 |
The \fIinput\fP and \fIoutput\fP arguments of
|
| 223 |
\fBpcre16_utf16_to_host_byte_order()\fP may point to the same address, that is,
|
| 224 |
conversion in place is supported. The output buffer must be at least as long as
|
| 225 |
the input.
|
| 226 |
.P
|
| 227 |
The \fIlength\fP argument specifies the number of 16-bit data units in the
|
| 228 |
input string; a negative value specifies a zero-terminated string.
|
| 229 |
.P
|
| 230 |
If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host
|
| 231 |
byte order. This may be changed by byte-order marks (BOMs) anywhere in the
|
| 232 |
string (commonly as the first character).
|
| 233 |
.P
|
| 234 |
If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it
|
| 235 |
points means that the input starts off in host byte order, otherwise the
|
| 236 |
opposite order is assumed. Again, BOMs in the string can change this. The final
|
| 237 |
byte order is passed back at the end of processing.
|
| 238 |
.P
|
| 239 |
If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied
|
| 240 |
into the output string. Otherwise they are discarded.
|
| 241 |
.P
|
| 242 |
The result of the function is the number of 16-bit units placed into the output
|
| 243 |
buffer, including the zero terminator if the string was zero-terminated.
|
| 244 |
.
|
| 245 |
.
|
| 246 |
.SH "SUBJECT STRING OFFSETS"
|
| 247 |
.rs
|
| 248 |
.sp
|
| 249 |
The offsets within subject strings that are returned by the matching functions
|
| 250 |
are in 16-bit units rather than bytes.
|
| 251 |
.
|
| 252 |
.
|
| 253 |
.SH "NAMED SUBPATTERNS"
|
| 254 |
.rs
|
| 255 |
.sp
|
| 256 |
The name-to-number translation table that is maintained for named subpatterns
|
| 257 |
uses 16-bit characters. The \fBpcre16_get_stringtable_entries()\fP function
|
| 258 |
returns the length of each entry in the table as the number of 16-bit data
|
| 259 |
units.
|
| 260 |
.
|
| 261 |
.
|
| 262 |
.SH "OPTION NAMES"
|
| 263 |
.rs
|
| 264 |
.sp
|
| 265 |
There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK,
|
| 266 |
which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
|
| 267 |
fact, these new options define the same bits in the options word. There is a
|
| 268 |
discussion about the
|
| 269 |
.\" HTML <a href="pcreunicode.html#utf16strings">
|
| 270 |
.\" </a>
|
| 271 |
validity of UTF-16 strings
|
| 272 |
.\"
|
| 273 |
in the
|
| 274 |
.\" HREF
|
| 275 |
\fBpcreunicode\fP
|
| 276 |
.\"
|
| 277 |
page.
|
| 278 |
.P
|
| 279 |
For the \fBpcre16_config()\fP function there is an option PCRE_CONFIG_UTF16
|
| 280 |
that returns 1 if UTF-16 support is configured, otherwise 0. If this option is
|
| 281 |
given to \fBpcre_config()\fP or \fBpcre32_config()\fP, or if the
|
| 282 |
PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to \fBpcre16_config()\fP,
|
| 283 |
the result is the PCRE_ERROR_BADOPTION error.
|
| 284 |
.
|
| 285 |
.
|
| 286 |
.SH "CHARACTER CODES"
|
| 287 |
.rs
|
| 288 |
.sp
|
| 289 |
In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the
|
| 290 |
same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
|
| 291 |
from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than
|
| 292 |
0xff can therefore be influenced by the locale in the same way as before.
|
| 293 |
Characters greater than 0xff have only one case, and no "type" (such as letter
|
| 294 |
or digit).
|
| 295 |
.P
|
| 296 |
In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
|
| 297 |
the exception of values in the range 0xd800 to 0xdfff because those are
|
| 298 |
"surrogate" values that are used in pairs to encode values greater than 0xffff.
|
| 299 |
.P
|
| 300 |
A UTF-16 string can indicate its endianness by special code knows as a
|
| 301 |
byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
|
| 302 |
to be in host byte order. A utility function called
|
| 303 |
\fBpcre16_utf16_to_host_byte_order()\fP is provided to help with this (see
|
| 304 |
above).
|
| 305 |
.
|
| 306 |
.
|
| 307 |
.SH "ERROR NAMES"
|
| 308 |
.rs
|
| 309 |
.sp
|
| 310 |
The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to
|
| 311 |
their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled
|
| 312 |
pattern is passed to a function that processes patterns in the other
|
| 313 |
mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to
|
| 314 |
\fBpcre16_exec()\fP.
|
| 315 |
.P
|
| 316 |
There are new error codes whose names begin with PCRE_UTF16_ERR for invalid
|
| 317 |
UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
|
| 318 |
are described in the section entitled
|
| 319 |
.\" HTML <a href="pcreapi.html#badutf8reasons">
|
| 320 |
.\" </a>
|
| 321 |
"Reason codes for invalid UTF-8 strings"
|
| 322 |
.\"
|
| 323 |
in the main
|
| 324 |
.\" HREF
|
| 325 |
\fBpcreapi\fP
|
| 326 |
.\"
|
| 327 |
page. The UTF-16 errors are:
|
| 328 |
.sp
|
| 329 |
PCRE_UTF16_ERR1 Missing low surrogate at end of string
|
| 330 |
PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate
|
| 331 |
PCRE_UTF16_ERR3 Isolated low surrogate
|
| 332 |
PCRE_UTF16_ERR4 Non-character
|
| 333 |
.
|
| 334 |
.
|
| 335 |
.SH "ERROR TEXTS"
|
| 336 |
.rs
|
| 337 |
.sp
|
| 338 |
If there is an error while compiling a pattern, the error text that is passed
|
| 339 |
back by \fBpcre16_compile()\fP or \fBpcre16_compile2()\fP is still an 8-bit
|
| 340 |
character string, zero-terminated.
|
| 341 |
.
|
| 342 |
.
|
| 343 |
.SH "CALLOUTS"
|
| 344 |
.rs
|
| 345 |
.sp
|
| 346 |
The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to
|
| 347 |
a callout function point to 16-bit vectors.
|
| 348 |
.
|
| 349 |
.
|
| 350 |
.SH "TESTING"
|
| 351 |
.rs
|
| 352 |
.sp
|
| 353 |
The \fBpcretest\fP program continues to operate with 8-bit input and output
|
| 354 |
files, but it can be used for testing the 16-bit library. If it is run with the
|
| 355 |
command line option \fB-16\fP, patterns and subject strings are converted from
|
| 356 |
8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions
|
| 357 |
are used instead of the 8-bit ones. Returned 16-bit strings are converted to
|
| 358 |
8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled,
|
| 359 |
\fBpcretest\fP defaults to 16-bit and the \fB-16\fP option is ignored.
|
| 360 |
.P
|
| 361 |
When PCRE is being built, the \fBRunTest\fP script that is called by "make
|
| 362 |
check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit,
|
| 363 |
16-bit and 32-bit libraries has been built, and runs the tests appropriately.
|
| 364 |
.
|
| 365 |
.
|
| 366 |
.SH "NOT SUPPORTED IN 16-BIT MODE"
|
| 367 |
.rs
|
| 368 |
.sp
|
| 369 |
Not all the features of the 8-bit library are available with the 16-bit
|
| 370 |
library. The C++ and POSIX wrapper functions support only the 8-bit library,
|
| 371 |
and the \fBpcregrep\fP program is at present 8-bit only.
|
| 372 |
.
|
| 373 |
.
|
| 374 |
.SH AUTHOR
|
| 375 |
.rs
|
| 376 |
.sp
|
| 377 |
.nf
|
| 378 |
Philip Hazel
|
| 379 |
University Computing Service
|
| 380 |
Cambridge CB2 3QH, England.
|
| 381 |
.fi
|
| 382 |
.
|
| 383 |
.
|
| 384 |
.SH REVISION
|
| 385 |
.rs
|
| 386 |
.sp
|
| 387 |
.nf
|
| 388 |
Last updated: 14 April 2012
|
| 389 |
Copyright (c) 1997-2012 University of Cambridge.
|
| 390 |
.fi
|
Parent Directory
| 
Revision Log